Chih-Hsuan Wang

An integrated approach for process monitoring using wavelet analysis and competitive neural network

A novel framework involving both a detection module and a classification module is proposed for the recognition of the six main types of process signals. In particular, a multi-scale wavelet filter is used for denoising and its performance is compared with that of single-scale linear filters. Moreover, two kinds of competitive neural networks, based on learning vector quantization (LVQ) and adaptive resonance theory (ART), are adopted for the task of pattern classification and benchmarking. Our results show that denoising through a wavelet filter is best for pattern classification, and the classification accuracy with respect to six predefined categories using a LVQ-X network is a little better than using an ART network. However, when an unexpected novel pattern occurs within the process, LVQ will force the novel pattern to be classified into one of those predefined categories that is most similar to the novel pattern. On the contrary, ART will automatically construct a new class when the similarity measured between the novel pattern and the most similar category is too small to be incorporated. Therefore, under the consideration of the stability–plasticity dilemma, our simplified ART network based on multi-scale wavelet denoising provides a more promising way to adapt unexpected novel patterns.

Using quality function deployment for collaborative product design and optimal selection of module mix

In response to fast-growing and rapidly-changing markets, launching new products faster than competitors cannot only assist firms in acquiring larger market share but also reducing development lead time, significantly. However, owing to its intrinsically uncertain properties of managing NPD (new product development), manufacturing companies often struggle with the dilemma of increasing product variety or controlling manufacturing complexity. In this study, a fuzzy MCDM (multi-criteria decision making) based QFD (quality function deployment) which integrates fuzzy Delphi, fuzzy DEMATEL (decision making trial and evaluation laboratory), with LIP (linear integer programming) is proposed to assist an enterprise in fulfilling collaborative product design and optimal selection of module mix when aiming at multi-segments. In particular, Fuzzy Delphi is adopted to gather marketing information from invited customers and their assessments of marketing requirements are pooled to reach a consensus; fuzzy DEMATEL is utilized to derive the priorities of technical attributes in a market-oriented manner; and LIP is used to maximize product capability with consideration of suppliers budget constraints of manufacturing resources. Furthermore, a real case study on developing various types of sport and water digital cameras is demonstrated to validate the proposed approach.

Identification of control chart patterns using wavelet filtering and robust fuzzy clustering

This paper proposes a hybrid framework composed of filtering module and clustering module to identify six common types of control chart patterns, including natural pattern, cyclic pattern, upward shift, downward shift, upward trend, and downward trend. In particular, a multi-scale wavelet filter is designed for denoising and its performance is compared to single-scale filters, including mean filter and exponentially weighted moving average (EWMA) filter. Moreover, three fuzzy clustering algorithms, based on fuzzy c means (FCM), entropy fuzzy c means (EFCM) and kernel fuzzy c means (KFCM), are adopted to compare their performance of pattern classification. Experimental results demonstrate that the excellent performance of EFCM and KFCM against outliers, especially in the case of high noise level embedded in the input data. Therefore, a hybrid framework combining wavelet filter with robust fuzzy clustering is suggested and proposed in this paper. Compared to neural network based approaches, the proposed method provides a promising way for the on-line recognition of control chart patterns because of its efficient computation and robustness against outliers.

Detection and classification of defect patterns on semiconductor wafers

The detection of process problems and parameter drift at an early stage is crucial to successful semiconductor manufacture. The defect patterns on the wafer can act as an important source of information for quality engineers allowing them to isolate production problems. Traditionally, defect recognition is performed by quality engineers using a scanning electron microscope. This manual approach is not only expensive and time consuming but also it leads to high misidentification levels. In this paper, an automatic approach consisting of a spatial filter, a classification module and an estimation module is proposed to validate both real and simulated data. Experimental results show that three types of typical defect patterns: (i) a linear scratch; (ii) a circular ring; and (iii) an elliptical zone can be successfully extracted and classified. A Gaussian EM algorithm is used to estimate the elliptic and linear patterns, and a spherical-shell algorithm is used to estimate ring patterns. Furthermore, both convex and nonconvex defect patterns can be simultaneously recognized via a hybrid clustering method. The proposed method has the potential to be applied to other industries.

Decision tree based control chart pattern recognition

This paper presents a new approach to classify six anomaly types of control chart patterns (CCP), of systematic pattern, cyclic pattern, upward shift, downward shift, upward trend, and downward trend. Current CCP recognition methods use either unprocessed raw data or complex transformed features (via principal component analysis or discrete wavelet transform) as the input representation for the classifier. The objective of using selected features is not only for dimension reduction of input representation, but also implies the process of data compression. In contrast, using raw data is often computationally inefficient while using transformed features is very tedious in most cases. Therefore, owing to its computational advantage, using appropriate features of CCP to achieve good classification accuracy becomes more promising in real process implementation. In this study, using three features of CCP shows quite a competitive performance in terms of classification accuracy and computational loading. More importantly, the proposed method presented here has potential to be generalized to medical, financial, and other application of temporal data.

Incorporating customer satisfaction into the decision-making process of product configuration: a fuzzy Kano perspective

In an era of global customisation, buyers continuously benefit from the flexibility of selecting their desired options when making decisions on purchasing. Most manufacturing companies, however, need to balance the trade-offs between enhancing product variety and controlling manufacturing cost. In order to fulfil the goal of market-oriented product development, customer satisfaction needs to be well incorporated into the decision-making process of product configuration. Therefore, a hybrid framework is presented to address two critical issues in new product development: customer satisfaction and product configuration. In the beginning, fuzzy Kano model is employed to elicit customer perception of product attributes and extract customer satisfaction. Consecutively, information entropy is used for deriving the important weights of product attributes. Lastly, by means of Technique for Order Preference by Similarity to Ideal Solution, competing design alternatives are efficiently prioritised and configured. In particular, a case study on configuring varieties of smart pads is demonstrated to justify the validity of the proposed framework. With consideration of and the pricing policies of multi-segments, a systematic framework to effectively bridge customer satisfaction and product configuration is offered for the academics and industrial practitioners.

Recognition of semiconductor defect patterns using spatial filtering and spectral clustering

Diverse defect patterns shown on the wafer map usually contain important information for quality engineers to find their root causes of abnormalities. Today, even with highly automated and precisely monitored facilities used in a near dust-free clean room and operated with well-trained process engineers, the occurrence of spatial defects still cannot be avoided. This research presents a spatial defect diagnosis system and attempts to solve two challenging problems for semiconductor manufacturing: (1) to estimate the number of clusters in advance, and (2) to separate both convex and non-convex defect clusters at the same time. In this paper, a spatial filter is used to denoise the noisy wafer map and to extract meaningful defect clusters. To isolate various types of defect patterns, a hybrid scheme combining entropy fuzzy c means (EFCM) with spectral clustering is applied to the denoised output. Furthermore, a decision tree based on two cluster features (convexity and eigenvalue ratio) is constructed to identify the specific defect type and to provide decision support for quality engineers. The proposed approach is validated with an empirical wafer bin maps obtained in a DRAM company in Taiwan. Experimental results show that four kinds of mixed-type defect patterns are successfully extracted and classified. More importantly, the proposed method is very promising to be further applied to other industries, such as liquid crystal or plasma display.

A hybrid approach for identification of concurrent control chart patterns

Control chart patterns (CCPs) are widely used to identify the potential process problems in modern manufacturing industries. The earliest statistical techniques, including

Automatic identification of spatial defect patterns for semiconductor manufacturing

{\bar{\rm X}}